Triple
T26398582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ATK |
E663639
|
entity |
| Predicate | mostISLTitles |
P67310
|
FINISHED |
| Object | one of the most successful ISL clubs |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: one of the most successful ISL clubs | Statement: [ATK, mostISLTitles, one of the most successful ISL clubs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mostISLTitles Context triple: [ATK, mostISLTitles, one of the most successful ISL clubs]
-
A.
ISLTitles
Indicates that one entity holds a title or designation that is recognized or defined by another entity.
-
B.
mastersTitles
Indicates that one entity holds one or more master's degree titles associated with another entity (such as an institution, field, or program).
-
C.
majorTitleWon
chosen
Indicates that an entity has won a significant or top-level title, championship, or major award in a given domain.
-
D.
mostSuccessfulProgramTitles
Indicates that the associated program titles are the ones with the highest level of success according to a specified metric (e.g., ratings, revenue, or impact) compared to other programs.
-
E.
USTitles
Indicates that the entity holds or is associated with official titles or designations specific to the United States.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69ee883823988190b418b111be28a44a |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f610f1f6508190a1540b6a7d3568f9 |
completed | May 2, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 11:30 p.m.